Optimizing nitrogen estimates in common bean canopies throughout key growth stages via fusion of spectral and textural data from unmanned aerial vehicle (UAV) multispectral imagery

This study investigates the potential of utilizing multispectral imagery acquired from unmanned aerial vehicles (UAVs) to enhance the accuracy of leaf nitrogen content (LNC) estimation, a crucial parameter for assessing crop nitrogen status and guiding nitrogen management practices. We integrated selected vegetation indices (VIs) and texture data (gray level co-occurrence matrix - GLCM) derived from UAV-based multispectral images to estimate LNC in common bean (Phaseolus vulgaris L.). Therefore, the objectives of this study were (i) to determine the optimal VIs and texture metrics from UAV multispectral imagery for estimating LNC, and (ii) to explore the capability of integrating spectral and textural information in the improvement of N status monitoring.

本研究探讨了利用无人机（unmanned aerial vehicles, UAV）获取的多光谱影像提升叶片氮含量（leaf nitrogen content, LNC）估算精度的潜力，而叶片氮含量是评估作物氮素营养状态、指导氮肥管理实践的关键参数。本研究整合了由无人机多光谱影像提取的优选植被指数（vegetation indices, VIs）与纹理数据（灰度共生矩阵（gray level co-occurrence matrix, GLCM）），以估算菜豆（Phaseolus vulgaris L.）的叶片氮含量。因此，本研究的目标为：(i) 确定适用于叶片氮含量估算的无人机多光谱影像最优植被指数与纹理指标；(ii) 探究整合光谱与纹理信息对提升氮素状态监测能力的作用效果。